Efficient Wait-k Models for Simultaneous Machine Translation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Efficient Wait-k Models for Simultaneous Machine Translation

Résumé

Simultaneous machine translation consists in starting output generation before the entire input sequence is available. Wait-k decoders offer a simple but efficient approach for this problem. They first read k source tokens, after which they alternate between producing a target token and reading another source token. We investigate the behavior of wait-k decoding in low resource settings for spoken corpora using IWSLT datasets. We improve training of these models using unidirectional encoders, and training across multiple values of k. Experiments with Transformer and 2D-convolutional architectures show that our wait-k models generalize well across a wide range of latency levels. We also show that the 2D-convolution architecture is competitive with Transformers for simultaneous translation of spoken language.
Fichier principal
Vignette du fichier
Waitk_decoding__InterSpeech_2020_.pdf (385.16 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02962195 , version 1 (09-10-2020)

Identifiants

Citer

Maha Elbayad, Laurent Besacier, Jakob Verbeek. Efficient Wait-k Models for Simultaneous Machine Translation. Interspeech 2020 - Conference of the International Speech Communication Association, Oct 2020, Shangai (Virtual Conf), China. pp.1461--1465, ⟨10.21437/Interspeech.2020-1241⟩. ⟨hal-02962195⟩
227 Consultations
193 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More